btw we're in the wrong channel, this is about stable diffusion
btw we're in the wrong channel, this is about stable diffusion
Fyes many times faster with batch size 4
Fso a6000 much better option
Fthis is also one of my aims
Fand a very useful one
Fbut i didnt have chance yet
F
F
F
F
BHello @Dr. Furkan Gözükara, do you offer a training video guide on how to train Stable Diffusion to apply a particular style to any prompt versus creating a specific model/person each time? For example, creating a model or LoRA to generate an image using a specific drawing/illustration style? Thank you
Also, is the part of your paid Patreon?
Also, is the part of your paid Patreon?
FHello. I am giving training
Fother than my videos
F1 hour is 100$ for individuals. 1 to 1 lecture
F
GHello i am looking for help about roop extension in stable diffusion. Could you please help me for that if i am copy past here the error?
BOk, thank you.
B@Dr. Furkan Gözükara, I watched your video (https://www.youtube.com/watch?v=AZg6vzWHOTA) on installing Stable Diffusion on Windows, however, the installer (https://github.com/EmpireMediaScience/A1111-Web-UI-Installer) is no longer maintained. Do you recommend another one-click installer for Windows?
YouTubeSECourses
Our Discord : https://discord.gg/HbqgGaZVmr. How to download and install Stable Diffusion Automatic1111 Web UI interface. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Goog...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Goog...
GitHub
Complete installer for Automatic1111's infamous Stable Diffusion WebUI - GitHub - EmpireMediaScience/A1111-Web-UI-Installer: Complete installer for Automatic1111's infamous Stable D...
SI used your Best 24GB settings and increased batch size to 2 while keeping everything else the same. To my surprise, this actually increased the total training time (it is very possible I screwed somethign else up). Are there any other settings you have to change to compensate for increased batch size? i.e. reduce num cpus per process?
S@Dr. Furkan Gözükara when not using regularization steps, do you find that less total number of training steps is necessary?
Fvery possibly c++ error
Fhave you installed it?
Fhello yes
Fi dont suggest it anymore
Finstall directly
Fi have shown in several videos recently
FYouTubeSECourses
Welcome to the Pillars of AI Application Libraries: How to Install Tutorial! 
Are you ready to embark on a journey of installing AI libraries and applications with ease? 
In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. 
We'll also show you ho...
Are you ready to embark on a journey of installing AI libraries and applications with ease? In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. We'll also show you ho...Fand this one
FYouTubeSECourses
Stable Diffusion Gets A Major Boost With RTX Acceleration. One of the most common ways to use Stable Diffusion, the popular Generative AI tool that allows users to produce images from simple text descriptions, is through the Stable Diffusion Web UI by Automatic1111. In today’s Game Ready Driver, NVIDIA added TensorRT acceleration for Stable Diff...
Fwhat is your GPU?
SThat is an A5000 on runpod. Running via cli though, rather than automatic1111, so I wonder if there is some settings that I'm missing. i.e. perhaps in automatic 1111, doubling the batch size will automatically half the total number of training steps?
GThanks for reply, i fixed just now. The error was because i didnt install insightface.
FA5000 cant run multiple batch size
Fbatch size 1 already uses 17 gb
Fyes it requires c++
Shmmm interesting, i haven't received an out of memory error on that with a batch size of 2
MHey guys, since I have to make an impression on the influencers based on a real one, I should slightly change their face with stable diffusion. In your opinion, how could it be done?
Fthen something must be wrong
Sokay gotcha. Yeah, I guess that should use double the amount of vram, exceeding what the a5000 can do
F40 gb card can do 3 batch size
F48 gb can do 4
Fi dont remember testing 2 on 24 
Sokay gotcha, thanks for that info
MI was thinking about controlNet, for you am I on the right way?
S@Dr. Furkan Gözükara when you use a batch size of 4 on a 48gb card, did you find you needed to adjust your learning rate?
Fye may work
Fi use same
Fbut i didnt test actually
Fhowever it works
Fi trained several times
